Provided are a method and an apparatus for analyzing a vibration of a deep-learning based washing machine. In the method for analyzing a vibration of a deep-learning based washing machine according to an embodiment of the present invention, a washing tub of the washing machine includes a specific shape pattern, an artificial neural network model is learned from a video image obtained by photographing the shape pattern through a camera and a vibration value sensed through the vibration sensor, and thus, by using the artificial neural network model, it is possible to predict a vibration value of the washing machine using the camera of the washing machine even without a vibration sensor. According to the present invention, a smart washing machine without the vibration sensor such as 6-axis gyro sensor can be implemented. The AI device of the present invention can be associated with an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, and a device related to a 5G service.